Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17602
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Super" followed by a number from 8 to 10

    oai_token-act-pair · gpt-3.5-turbo

    references to "Super" associated with various contexts or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gow
    -0.86
     Seym
    -0.78
    assetsadobe
    -0.77
    76561
    -0.68
    asus
    -0.67
    OPLE
    -0.65
     Greenwald
    -0.64
    edIn
    -0.64
     guiActiveUn
    -0.63
    ered
    -0.63
    POSITIVE LOGITS
    visors
    1.26
    visor
    1.26
    imposed
    1.11
    markets
    1.09
    natural
    1.06
    nova
    1.04
    visory
    1.04
    marine
    1.03
    charg
    0.99
    vised
    0.97
    Activations Density 0.015%

    No Known Activations